© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 10456
    Prev
    Next
    INDEX
    Explanations

    size of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parity
    -0.10
    bedo
    -0.09
     achie
    -0.09
     Esper
    -0.09
     parity
    -0.08
    uÄį
    -0.08
    _drawer
    -0.08
    tring
    -0.08
     level
    -0.08
    ogn
    -0.08
    POSITIVE LOGITS
     size
    0.15
    -scale
    0.14
     audiences
    0.12
     footprint
    0.12
     vocabulary
    0.12
     vocab
    0.12
     dataset
    0.12
    /tiny
    0.11
     sized
    0.11
    ocabulary
    0.11
    Activations Density 0.061%

    No Known Activations